Replace with baseline PR47 recipe artifacts (listening-validated engine)

README.md

@@ -15,10 +15,9 @@ tags:
 FP8 GEMM-trunk quantization of the Stable Audio 3 medium DiT, built from
 `stabilityai/stable-audio-3-optimized` `onnx/sa3-m/dit_fp16mixed.onnx` with the
 producer recipe in [Stability-AI/stable-audio-3 PR #47](https://github.com/Stability-AI/stable-audio-3/pull/47)
-(`build/make_calib.py` + `build/build_dit_fp8.py`), including the
-dequant-front-end recipe step. This is a derivative of Stability AI's model
-weights and is distributed under the Stability AI Community License; see the
-base model for terms.
+(`build/make_calib.py` + `build/build_dit_fp8.py`). This is a derivative of
+Stability AI's model weights and is distributed under the Stability AI
+Community License; see the base model for terms.
 
 ## Contents
 
@@ -31,10 +30,14 @@ base model for terms.
 
 ## Validation (vs the FP16-mixed engine, 47 prompts x 8 sigmas, L=646, RTX 5090)
 
-- worst single-step latent cosine (x + dt*v): 0.9993 (n=376)
-- 8-step compounded final-latent cosine over 47 prompts: mean 0.967,
-  median 0.972, worst 0.901 (the rollout is chaotic; a 1e-3 input
+- worst single-step latent cosine (x + dt*v, n=376): 0.9982
+- 8-step compounded euler final-latent cosine over 47 prompts: mean 0.953,
+  median 0.957, worst 0.873 (the rollout is chaotic; a 1e-3 input
   perturbation alone compounds to ~0.967, so this is a guide, not a gate)
+- decoded audio under the production pingpong sampler tracks the FP16-mixed
+  generation at ~0.90 RMS-curve correlation (same conditioning and seeds) and
+  was validated by listening: the published sm_120 engine here is the exact
+  engine that passed that test
 - step latency B=1 L=646: ~10.6-11.0 ms vs ~18.7-19.4 ms FP16-mixed (~1.8x)
 - under the stochastic pingpong sampler the engine produces a different but
   comparable sample

onnx/sa3-m/dit_fp8.onnx

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:af67c494125d1081a3d2d769ceec454d32be3237b46d9de8843a69fd45571758
-size 12382984
+oid sha256:c4b4bafb3de4f7d7abc1c3f294eaad8276f2251f5c60ef538b468a7c8074c460
+size 12414124

tensorRT/sm_120/sa3-m/dit_fp8.trt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6ed8394389ccb9389805d6833a537cd0d249e796ad9e9d777ccfcb68d1addfdc
-size 1498263724
+oid sha256:674a3ba7d4b52383edbcd2fffcb1b224fd710e6de19ae947af680b5b54cd3991
+size 1493783180